Open Data for Global Multimodal Land Use Classification: Outcome of the 2017 IEEE GRSS Data Fusion Contest

Naoto Yokoya, Pedram Ghamisi, Junshi Xia, Sergey Sukhanov, Roel Heremans, Ivan Tankoyeu, Benjamin Bechtel, Bertrand Le Saux, Gabriele Moser, Devis Tuia

Research output: Contribution to journalArticleAcademicpeer-review

24 Citations (Scopus)

Abstract

In this paper, we present the scientific outcomes of the 2017 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2017 Contest was aimed at addressing the problem of local climate zones classification based on a multitemporal and multimodal dataset, including image (Landsat 8 and Sentinel-2) and vector data (from OpenStreetMap). The competition, based on separate geographical locations for the training and testing of the proposed solution, aimed at models that were accurate (assessed by accuracy metrics on an undisclosed reference for the test cities), general (assessed by spreading the test cities across the globe), and computationally feasible (assessed by having a test phase of limited time). The techniques proposed by the participants to the Contest spanned across a rather broad range of topics, and of mixed ideas and methodologies deriving from computer vision and machine learning but also deeply rooted in the specificities of remote sensing. In particular, rigorous atmospheric correction, the use of multidate images, and the use of ensemble methods fusing results obtained from different data sources/time instants made the difference.
LanguageEnglish
Pages1363-1377
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Volume11
Issue number5
DOIs
Publication statusPublished - 16 Apr 2018

Fingerprint

Data fusion
Land use
Remote sensing
Image analysis
Computer vision
Learning systems
remote sensing
computer vision
atmospheric correction
Testing
image analysis
Landsat
methodology
land use classification
climate
test
city

Cite this

Yokoya, Naoto ; Ghamisi, Pedram ; Xia, Junshi ; Sukhanov, Sergey ; Heremans, Roel ; Tankoyeu, Ivan ; Bechtel, Benjamin ; Le Saux, Bertrand ; Moser, Gabriele ; Tuia, Devis. / Open Data for Global Multimodal Land Use Classification: Outcome of the 2017 IEEE GRSS Data Fusion Contest. In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2018 ; Vol. 11, No. 5. pp. 1363-1377.
@article{9d114c1d33ad49b8a16070029a422666,
title = "Open Data for Global Multimodal Land Use Classification: Outcome of the 2017 IEEE GRSS Data Fusion Contest",
abstract = "In this paper, we present the scientific outcomes of the 2017 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2017 Contest was aimed at addressing the problem of local climate zones classification based on a multitemporal and multimodal dataset, including image (Landsat 8 and Sentinel-2) and vector data (from OpenStreetMap). The competition, based on separate geographical locations for the training and testing of the proposed solution, aimed at models that were accurate (assessed by accuracy metrics on an undisclosed reference for the test cities), general (assessed by spreading the test cities across the globe), and computationally feasible (assessed by having a test phase of limited time). The techniques proposed by the participants to the Contest spanned across a rather broad range of topics, and of mixed ideas and methodologies deriving from computer vision and machine learning but also deeply rooted in the specificities of remote sensing. In particular, rigorous atmospheric correction, the use of multidate images, and the use of ensemble methods fusing results obtained from different data sources/time instants made the difference.",
author = "Naoto Yokoya and Pedram Ghamisi and Junshi Xia and Sergey Sukhanov and Roel Heremans and Ivan Tankoyeu and Benjamin Bechtel and {Le Saux}, Bertrand and Gabriele Moser and Devis Tuia",
year = "2018",
month = "4",
day = "16",
doi = "10.1109/JSTARS.2018.2799698",
language = "English",
volume = "11",
pages = "1363--1377",
journal = "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing",
issn = "1939-1404",
publisher = "Institute of Electrical and Electronics Engineers",
number = "5",

}

Open Data for Global Multimodal Land Use Classification: Outcome of the 2017 IEEE GRSS Data Fusion Contest. / Yokoya, Naoto; Ghamisi, Pedram; Xia, Junshi; Sukhanov, Sergey; Heremans, Roel; Tankoyeu, Ivan; Bechtel, Benjamin; Le Saux, Bertrand; Moser, Gabriele; Tuia, Devis.

In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 11, No. 5, 16.04.2018, p. 1363-1377.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Open Data for Global Multimodal Land Use Classification: Outcome of the 2017 IEEE GRSS Data Fusion Contest

AU - Yokoya, Naoto

AU - Ghamisi, Pedram

AU - Xia, Junshi

AU - Sukhanov, Sergey

AU - Heremans, Roel

AU - Tankoyeu, Ivan

AU - Bechtel, Benjamin

AU - Le Saux, Bertrand

AU - Moser, Gabriele

AU - Tuia, Devis

PY - 2018/4/16

Y1 - 2018/4/16

N2 - In this paper, we present the scientific outcomes of the 2017 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2017 Contest was aimed at addressing the problem of local climate zones classification based on a multitemporal and multimodal dataset, including image (Landsat 8 and Sentinel-2) and vector data (from OpenStreetMap). The competition, based on separate geographical locations for the training and testing of the proposed solution, aimed at models that were accurate (assessed by accuracy metrics on an undisclosed reference for the test cities), general (assessed by spreading the test cities across the globe), and computationally feasible (assessed by having a test phase of limited time). The techniques proposed by the participants to the Contest spanned across a rather broad range of topics, and of mixed ideas and methodologies deriving from computer vision and machine learning but also deeply rooted in the specificities of remote sensing. In particular, rigorous atmospheric correction, the use of multidate images, and the use of ensemble methods fusing results obtained from different data sources/time instants made the difference.

AB - In this paper, we present the scientific outcomes of the 2017 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2017 Contest was aimed at addressing the problem of local climate zones classification based on a multitemporal and multimodal dataset, including image (Landsat 8 and Sentinel-2) and vector data (from OpenStreetMap). The competition, based on separate geographical locations for the training and testing of the proposed solution, aimed at models that were accurate (assessed by accuracy metrics on an undisclosed reference for the test cities), general (assessed by spreading the test cities across the globe), and computationally feasible (assessed by having a test phase of limited time). The techniques proposed by the participants to the Contest spanned across a rather broad range of topics, and of mixed ideas and methodologies deriving from computer vision and machine learning but also deeply rooted in the specificities of remote sensing. In particular, rigorous atmospheric correction, the use of multidate images, and the use of ensemble methods fusing results obtained from different data sources/time instants made the difference.

U2 - 10.1109/JSTARS.2018.2799698

DO - 10.1109/JSTARS.2018.2799698

M3 - Article

VL - 11

SP - 1363

EP - 1377

JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

T2 - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

SN - 1939-1404

IS - 5

ER -